Estimating Spatiotemporal Information from Behavioral Sensing Data of Wheelchair Users by Machine Learning Technologies

Abstract

Recent expansion of intelligent gadgets, such as smartphones and smart watches, familiarizes humans with sensing their activities. We have been developing a road accessibility evaluation system inspired by human sensing technologies. This paper introduces our methodology to estimate road accessibility from the three-axis acceleration data obtained by a smart phone attached on a wheelchair seat, such as environmental factors, e.g., curbs and gaps, which directly influence wheelchair bodies, and human factors, e.g., wheelchair users’ feelings of tiredness and strain. Our goal is to realize a system that provides the road accessibility visualization services to users by online/offline pattern matching using impersonal models, while gradually learning to improve service accuracy using new data provided by users. As the first step, this paper evaluates features acquired by the DCNN (deep convolutional neural network), which learns the state of the road surface from the data in supervised machine learning techniques. The evaluated results show that the features can capture the difference of the road surface condition in more detail than the label attached by us and are effective as the means for quantitatively expressing the road surface condition. This paper developed and evaluated a prototype system that estimated types of ground surfaces focusing on knowledge extraction and visualization.

Strategically using Applied Machine Learning for Accessibility Documentation in the Built Environment

“…In an ideal world, the most effective approach towards accessibility documentation would be an automated one, given the relatively lower cost. There are numerous works that claim to offer a viable system for using inertial sensors mounted on mobility aids (e.g., wheelchairs) to measure the accessibility of the built environment [38,39,40,51,77]. Unfortunately the evaluations that are said support these claims are based on 'toy problems' in respect of the data being collected in a laboratory rather than in the real world (meaning the findings are unlike to apply there [63].…”

Weakly Supervised Learning for Evaluating Road Surface Condition from Wheelchair Driving Data

“…Human activities measured by body-mounted vital sensors are recognized by applying machine learning [12,13]. Motivated by this background, we proposed a system that evaluates road surface conditions by applying machine learning to wheelchair accelerometer data [14]. Notably, wheelchair driving data can be collected extensively and are influenced by subtle road surface conditions.…”